Agriculture is the most primary and indispensable source to furnish national income of numerous countries including India. Diseases in plants/crops are the serious causes in degrading the production quantity and quality, which results in economy losses. Thus, identification of the diseases in plants is very important. Plant disease symptoms are evident in various parts of plants. However, plant leaves are most commonly used to detect the infection. Computer vision and soft computing techniques are utilized by several researchers to automate the detection of plant diseases using leaf images. Various aspects of such studies with their merits and demerits are summarized in this work. Common infections along with the research landscape at different stages of such detection systems are discussed. The modern feature extraction techniques are analyzed for identifying those that appear to work well covering several crop categories. The study would help the researchers to understand the applicability of computer vision in plant disease detection/classification.

农业是包括印度在内的许多国家的国民收入的最主要，必不可少的来源。植物/作物中的病害是导致产量和质量下降的严重原因，从而导致经济损失。因此，鉴定植物中的疾病非常重要。植物病害症状在植物的各个部位都很明显。但是，植物叶片最常用于检测感染。几位研究人员利用计算机视觉和软计算技术来利用叶图像自动检测植物病害。这项工作总结了这类研究的各个方面，各有其优缺点。讨论了这种检测系统不同阶段的常见感染以及研究前景。对现代特征提取技术进行了分析，以识别在几种作物类别中看起来效果很好的技术。该研究将有助于研究人员了解计算机视觉在植物病害检测/分类中的适用性。